NEURAL NETWORK DEVICE AND SYNAPTIC WEIGHT UPDATE METHOD

Organization Name

Inventor(s)

Yoshifumi Nishi of Yokohama Kanagawa (JP)

Koichi Mizushima of Kamakura Kanagawa (JP)

NEURAL NETWORK DEVICE AND SYNAPTIC WEIGHT UPDATE METHOD - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240296325 titled 'NEURAL NETWORK DEVICE AND SYNAPTIC WEIGHT UPDATE METHOD

The neural network device described in the abstract consists of neuron circuits, synapse circuits, and random number circuits. Each random number circuit outputs a random signal, which is used by synapse circuits to update synaptic weights based on the received signal. The synapse circuits are organized into groups, with each group receiving random signals from specific random number circuits.

Neuron circuits, synapse circuits, and random number circuits are key components of the neural network device.
Random number circuits generate random signals, which are utilized by synapse circuits to update synaptic weights.
Synapse circuits are divided into groups, with each group receiving random signals from specific random number circuits.
The organization of synapse circuits into groups helps in efficiently processing and updating synaptic weights in the neural network device.
This innovative design enhances the performance and adaptability of the neural network device.

Potential Applications: - Artificial intelligence systems - Machine learning algorithms - Robotics - Pattern recognition systems

Problems Solved: - Efficient updating of synaptic weights in neural networks - Improved adaptability and performance of neural network devices

Benefits: - Enhanced learning capabilities - Faster processing speeds - Increased accuracy in pattern recognition tasks

Commercial Applications: Title: "Advanced Neural Network Device for Enhanced Learning and Adaptability" This technology can be utilized in various industries such as: - Healthcare for medical diagnosis - Finance for fraud detection - Automotive for autonomous driving systems

Questions about the technology: 1. How does the organization of synapse circuits into groups improve the efficiency of the neural network device? 2. What are the potential limitations of using random number circuits in updating synaptic weights in neural networks?

Frequently Updated Research: Stay updated on the latest advancements in neural network devices and their applications in artificial intelligence and machine learning research.

Original Abstract Submitted

a neural network device according to an embodiment includes a plurality of neuron circuits, a plurality of synapse circuits, and a plurality of random number circuits. each of the random number circuits outputs a random signal. each of the synapse circuits receives the random signal from one of the random number circuits and updates a synaptic weight with a probability generated on the basis of the received random signal. the synapse circuits are divided into synapse groups. each of two or more synapse circuits belonging to a first synapse group receives the random signal output from a first random number circuit. each of two or more synapse circuits outputting output signals to a first neuron circuit belongs to a synapse group differing from a synapse group, to which other synapse circuits outputting the output signal to the first neuron circuit, belong.